|
Abdul Mohaimen Al Radi I'm a research assistant at the Cognitive Agents and Interaction Lab at the University of Dhaka, Dhaka, Bangladesh, where I work on different computer vision related projects such as, Image Deblurring, Generative Models, 3D reconstruction, and Segmentation My long-term research goal is to democratize AI, focusing on the field of computer vision. Steer the world closer towards AGI. Contribute meaningfully in tandem with healthcare. My goal with PhD is to gain necessary research expertise to achieve my ambitions, mentor people, and work to establish a lab in line with my research ethos. Seeking PhD position for Fall 2025 |
|
ResearchI'm interested in image restoration, multi-modal learning, medical image analysis, 3D reconstruction, and generative models. I'm particularly interested in developing algorithms that can learn from small data and generalize well to new tasks. I'm also interested in the intersection of computer vision and healthcare, and I'm excited about the potential for AI to improve patient outcomes and reduce healthcare costs. |
Education |
|
University of Dhaka BS.c in Computer Science and Engineering, (CGPA 3.72/4.00), top 10% of class Jan 2019 - Jan 2024 |
Sharp
Blurry
|
Blind Image Deblurring with FFT-ReLU Sparsity Prior
Abdul Mohaimen Al Radi*, Prothito Shovon Majumder*, Md Mosaddek Khan, WACV, 2025 download Blind image deblurring is the process of recovering a sharp image from a blurred one without prior knowledge about the blur kernel. It is a small data problem, since the key challenge lies in estimating the unknown degrees of blur from a single image or limited data, instead of learning from large datasets. The solution depends heavily on developing algorithms that effectively model the image degradation process. We introduce a method that leverages a prior which targets the blur kernel to achieve effective deblurring across a wide range of image types. In our extensive empirical analysis, our algorithm achieves results that are competitive with the state-of-the-art blind image deblurring algorithms, and it offers up to two times faster inference, making it a highly efficient solution. |
|
Vision Transformer and FFT-ReLU Fusion for Advanced Image Deblurring
Syed Mumtahin Mahmud Mahdi Mohd Hossain Noki1 Prothito Shovon Majumder, Abdul Mohaimen Al Radi/, Md. Haider Ali Md Mosaddek Khan, Under Review download We propose a novel approach to blind image deblurring that combines Vision Transformers with Fast Fourier Transform (FFT) and ReLU sparsity priors. Our method efficiently captures both local and global features while targeting blur-related frequencies, achieving competitive results with state-of-the-art methods at faster inference speeds. Through extensive experiments on benchmark datasets and human evaluations, we demonstrate that our technique produces high-quality results across diverse image types, making it well-suited for real-world applications. |
|
An end-to-end authentication mechanism for wireless body area networks
Mosarrat Jahan, Fatema Tuz Zohra, Md Kamal Parvez, Upama Kabir, Abdul Mohaimen Al Radi, Md. Haider Ali Shaily Kabir, Smart Health, By Elsevier, 2023 Journal This paper presents a secure authentication scheme for Wireless Body Area Networks (WBAN) in healthcare. Unlike existing approaches that assume patients' phones are trustworthy, our method treats phones as semi-trusted while enabling secure communication between medical sensors and healthcare providers. Analysis shows the scheme is both secure against attacks and efficient in real-world conditions. |
News |
| One paper accepted at WACV 2025 🔥 |
Work Experience |
|
Research Collaborator, University of Dhaka, |
|
Research Assistant, Cognitive Agents and Interaction Lab, University of Dhaka |
Additional Experience |
Workshops |
Hands on Deep Learning and Open Source Large Language Models, 2024 |
|
© Abdul Mohaimen Al Radi Template from Jon Barron |